© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12443
    Prev
    Next
    INDEX
    Explanations

    terms related to the abbreviation "SS" with varying levels of significance

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular medical condition denoted as "SS"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.84
    tics
    -0.76
    olulu
    -0.72
     Advertisement
    -0.70
    ãĥ£
    -0.68
    microsoft
    -0.68
     vain
    -0.67
     POLITICO
    -0.67
    framework
    -0.66
     McCartney
    -0.65
    POSITIVE LOGITS
    BM
    1.00
    SS
    0.92
    avorite
    0.92
    emen
    0.84
    MU
    0.83
    HT
    0.81
    agogue
    0.79
    gt
    0.78
    VD
    0.78
    antam
    0.77
    Activations Density 0.006%

    No Known Activations